© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 237681
    Prev
    Next
    INDEX
    Explanations

    governs falling bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ہمارا
    0.45
    亚马逊
    0.44
    Nodo
    0.44
    美国的
    0.42
    Nums
    0.42
     símbolo
    0.42
    Aqui
    0.42
    币
    0.42
     freaking
    0.41
    当我
    0.41
    POSITIVE LOGITS
     област
    0.53
     foodstuffs
    0.46
    RELATES
    0.44
     ಸಲ್ಲ
    0.43
     bienn
    0.43
     governs
    0.43
    🍶
    0.43
    🐟
    0.42
    iş
    0.42
     внесен
    0.41
    Activations Density 0.001%

    No Known Activations